Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
whisper-tiny-da – AI Model by HollowVoice | AlphaNeural AI
You can deploy this model and start earning money today!
HollowVoice
/
whisper-tiny-da
like
0
transformers
pytorch
tensorboard
whisper
automatic-speech-recognition
generated_from_trainer
da
audiofolder
model-index
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
Whisper Tiny Da - HollowVoice
This model is a fine-tuned version of
openai/openai/whisper-tiny
on the audiofolder dataset. It achieves the following results on the evaluation set:
Loss: 0.5216
Wer: 86.4999
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
learning_rate: 1e-05
train_batch_size: 16
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
training_steps: 4000
mixed_precision_training: Native AMP
Training results
Training Loss
Epoch
Step
Validation Loss
Wer
0.0319
24.39
1000
0.5216
86.4999
0.0031
48.78
2000
0.5156
89.3545
0.0017
73.17
3000
0.5267
89.7342
0.0013
97.56
4000
0.5312
90.9781
Framework versions
Transformers 4.27.0.dev0
Pytorch 1.13.1+cu117
Datasets 2.10.1
Tokenizers 0.13.2
